import geopandas as gpd

import matplotlib as plt

import pandas as pd

import seaborn as sns

import pandas_profiling

import mplleaflet as leaflet

from matplotlib.ticker import PercentFormatter

import matplotlib.pyplot as plt

import random as rnd

%matplotlib inline

all_data = gpd.read_file('outputs/newvars_surveys.geojson')

#Dropping variables

all_data.drop(columns = ["geometry"],inplace = True)

all_data.drop(['index_right'], axis=1, inplace=True)

all_data = pd.DataFrame(all_data)

#cat and num variables

catvars = all_data.select_dtypes(include=['object','bool']).columns

numvars = all_data.select_dtypes(include=['int64','float64']).columns

#Dropping outliers

merma_drop = all_data[all_data["cant_merma"] > 30].index

num_entregas_drop = all_data[all_data["num_entregas_fv"] >15 ].index

carga_drop = all_data[all_data["cant_carga"] > 350].index

​

all_data.drop([merma_drop[0],merma_drop[1]],inplace = True)

all_data.drop([num_entregas_drop[0]],inplace = True)

all_data.drop([i for i in carga_drop], inplace = True)

all_data.drop([i for i in all_data[all_data["cant_sku"] > 40].index], inplace = True)

​

 all_data[all_data["cant_carga"] > 350]

rnd.uniform(-all_data["cant_carga"].describe()[2],all_data["cant_carga"].describe()[2])

#Group by districts for zone

​

north_lima = ["CARABAYLLO","COMAS", "INDEPENDENCIA","LOS OLIVOS", "PUENTE PIEDRA","SAN MARTIN DE PORRES","ANCON",

              "SANTA ROSA"]

south_lima = ["CHORRILLOS","LURIN","PACHACAMAC","VILLA EL SALVADOR"]

​

east_lima = ["SAN JUAN DE LURIGANCHO","ATE","LA MOLINA"]

​

center_lima = ["SURQUILLO","SAN MIGUEL","BARRANCO",

               "SANTIAGO DE SURCO","SAN MIGUEL",

               "CHORRILLOS", "PUEBLO LIBRE",

               "LINCE","MAGDALENA DEL MAR"]

def zona(x):

    if x in north_lima:

        return "north_lima"

    elif x in south_lima:

        return "south_lima"

    elif x in east_lima:

        return "east_lima"

    elif x in center_lima:

        return "center_lima"

all_data["zone"] = all_data["distrito"].apply(zona)

pandas_profiling.ProfileReport(all_data)

# See any important correlation in numerical values

sns.pairplot(all_data[numvars])

plt.show()

all_data[]

#Actual correlation for numeric values

for cat in numvars:

    for cat2 in numvars:

        a = all_data[cat].corr(all_data[cat2])

        if (a > 0.6) and (a<1) and (cat!=cat2):

            print("{} vs {} :".format(cat,cat2) )

            print(a)

sns.relplot(x='cant_carga', y="cant_merma", hue='superficie_bodega', size = "superficie_bodega", data=all_data)

all_data[['hora_apertura_semana (hour)','hora_apertura_semana (minute)', 'hora_apertura_semana (seconds)']] = all_data.hora_apertura_semana.str.split(':', expand=True).astype(float)

all_data[['hora_cierre_semana (hour)','hora_cierre_semana (minute)','hora_cierre_semana (seconds)']] = all_data.hora_cierre_semana.str.split(':', expand=True).astype(float)

all_data[['hora_apertura_fin_de_semana (hour)','hora_apertura_fin_de_semana (minute)','hora_apertura_fin_de_semana (seconds)']] = all_data.hora_apertura_fin_de_semana.str.split(':', expand=True).astype(float)

all_data[['hora_cierre_fin_de_semana (hour)','hora_cierre_fin_de_semana (minute)','hora_cierre_fin_de_semana (seconds)']] = all_data.hora_cierre_fin_de_semana.str.split(':', expand=True).astype(float)

g = sns.catplot(x='hora_apertura_semana (hour)', kind="count", data=all_data)

g = sns.catplot(x='hora_cierre_semana (hour)', kind="count", data=all_data)

sns.relplot(y='betweenness_centrality_avg', x="cadena_frio", data=all_data)